通信学报 ›› 2021, Vol. 42 ›› Issue (7): 211-219.doi: 10.11959/j.issn.1000-436x.2021129

• 学术通信 • 上一篇    下一篇

快时变FDD大规模MIMO系统智能CSI反馈方法

廖勇, 王帅, 孙宁   

  1. 重庆大学微电子与通信工程学院,重庆 400044
  • 修回日期:2021-04-06 出版日期:2021-07-25 发布日期:2021-07-01
  • 作者简介:廖勇(1982− ),男,四川自贡人,博士,重庆大学副研究员、博士生导师,主要研究方向为下一代无线通信、人工智能、区块链、量子计算及其在无线通信中的应用等
    王帅(1995− ),男,安徽马鞍山人,重庆大学硕士生,主要研究方向为智能信号与信息处理
    孙宁(1995− ),男,河南长垣人,重庆大学硕士生,主要研究方向为智能信号与信息处理
  • 基金资助:
    国家自然科学基金资助项目(61501066);重庆市自然科学基金资助项目(cstc2019jcyj-msxmX0017)

Intelligent CSI feedback method for fast time-varying FDD massive MIMO system

Yong LIAO, Shuai WANG, Ning SUN   

  1. School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
  • Revised:2021-04-06 Online:2021-07-25 Published:2021-07-01
  • Supported by:
    The National Natural Science Foundation of China(61501066);The Natural Science Foundation of Chongqing(cstc2019jcyj-msxmX0017)

摘要:

针对快时变频分双工(FDD)大规模多输入多输出(MIMO)系统中因无线信道干扰使信道状态信息(CSI)矩阵中存在噪声以及多普勒频移导致的时间相关性使系统无法保证高可靠和低时延通信的问题,提出一种智能CSI反馈方法。该方法利用卷积神经网络(CNN)和批标准化(BN)网络对CSI矩阵中的噪声进行提取并且学习信道的空间结构,通过注意力机制提取CSI矩阵间的时间相关性以提高CSI重构的精度。利用标准的快时变信道模型仿真产生的数据对网络进行离线训练。系统仿真与分析表明,所提方法能够有效地抑制噪声的影响以及对多普勒引起的时间相关性进行提取。与代表性CSI压缩反馈方法和CsiNet方法相比,所提方法拥有更好的归一化均方误差(NMSE)和余弦相似度性能。

关键词: 快时变, 频分双工, 大规模多输入多输出, 压缩反馈, 信道状态信息, 智能反馈

Abstract:

In the frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) system, the channel state information (CSI) matrix existed noise caused by the wireless channel interference and the time correlation caused by Doppler shift.Because of these effects, the communication system couldn’t guarantee the requirements of reliability and low delay.An intelligent CSI feedback method was adopted.The convolutional neural network (CNN) and batch normalization (BN) network was used to extract the noise in the CSI matrix and learned the spatial structure of the channel.The time correlation between the CSI matrices through the attention mechanism was extracted to improve the accuracy of CSI reconstruction.The data was generated by the standard fast time-varying channel model simulation to train the network offline.System simulation and analysis show that the proposed method can effectively suppress the influence of noise and extract the time correlation caused by Doppler.Compared with the traditional CSI compression feedback algorithm and CsiNet algorithm, the proposed method has better NMSE and cosine similarity performance.

Key words: fast time-varying, FDD, massive MIMO, compression feedback, channel state information, feedback

中图分类号: 

No Suggested Reading articles found!